nsivabalan commented on issue #5223:
URL: https://github.com/apache/hudi/issues/5223#issuecomment-1125505391
```
import org.apache.hudi.QuickstartUtils._
import scala.collection.JavaConversions._
import org.apache.spark.sql.SaveMode._
import org.apache.spark.sql.functions._
import org.apache.hudi.DataSourceReadOptions._
import org.apache.hudi.DataSourceWriteOptions._
import org.apache.hudi.config.HoodieWriteConfig._
val inputDataset = "PATH_TO_PARQUET_DATASET"
val hudiBasePath = "/tmp/hudi/tbl1"
val hudiTableName = "tbl1"
val df = spark.read.format("parquet").load(inputDataset)
spark.time(df.write.format("hudi").
option(OPERATION_OPT_KEY,"bulk_insert").
option(PRECOMBINE_FIELD_OPT_KEY, "tpep_dropoff_datetime").
option(RECORDKEY_FIELD_OPT_KEY, "date_col").
option(TABLE_NAME, hudiTableName).
option("hoodie.parquet.compression.codec", "SNAPPY").
option("hoodie.write.markers.type","DIRECT").
option("hoodie.embed.timeline.server","false").
option("hoodie.bulkinsert.shuffle.parallelism","12").
option("hoodie.metadata.enable", "false").
option("hoodie.parquet.max.file.size","10485760").
option("hoodie.datasource.write.keygenerator.class","org.apache.hudi.keygen.NonpartitionedKeyGenerator").
mode(Overwrite).
save(hudiBasePath))
// read hudi
val hudiDf = spark.read.format("hudi").load(hudiBasePath)
hudiDf.registerTempTable("tbl1")
spark.sql("select count(*) from tbl1").show()
// trigger clustering
spark.time(df.limit(10000).write.format("hudi").
option(OPERATION_OPT_KEY,"bulk_insert").
option(PRECOMBINE_FIELD_OPT_KEY, "tpep_dropoff_datetime").
option(RECORDKEY_FIELD_OPT_KEY, "date_col").
option(TABLE_NAME, hudiTableName).
option("hoodie.parquet.compression.codec", "SNAPPY").
option("hoodie.write.markers.type","DIRECT").
option("hoodie.embed.timeline.server","false").
option("hoodie.bulkinsert.shuffle.parallelism","12").
option("hoodie.metadata.enable", "false").
option("hoodie.parquet.max.file.size","10485760").
option("hoodie.clustering.inline.max.commits","1").
option("hoodie.clustering.inline","true").
option("hoodie.clustering.plan.strategy.target.file.max.bytes","1073741824").
option("hoodie.datasource.write.keygenerator.class","org.apache.hudi.keygen.NonpartitionedKeyGenerator").
mode(Append).
save(hudiBasePath))
// read hudi
val hudiDf = spark.read.format("hudi").load(hudiBasePath)
hudiDf.registerTempTable("tbl1")
spark.sql("select count(*) from tbl1").show()
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
